Cleaning scripts:
Load data:
Visualize probability ratings
exp_trials = rbind(exp_trials1, exp_trials2, exp_trials3, exp_trials4, exp_trials5, exp_trials6)
exp_trials$prob = factor(exp_trials$prob)
ggplot(data = exp_trials) +
geom_boxplot(mapping = aes(x = prob, y = prob_rating, fill = prob))

Visualize mood ratings
mood1 = format_mood(read.csv("../../06_exp_away/data/06_exp_away_cond1-mood_ratings.csv"))
mood1$Answer.condition = "optimist"
mood2 = format_mood(read.csv("../../04_exp_away/data/04_exp_away_cond2-mood_ratings.csv"))
mood2$Answer.condition = "confident"
mood3 = format_mood(read.csv("../../04_exp_away/data/04_exp_away_cond3-mood_ratings.csv"))
mood3$Answer.condition = "pessimist"
mood4 = format_mood(read.csv("../../04_exp_away/data/04_exp_away_cond4-mood_ratings.csv"))
mood4$Answer.condition = "cautious"
mood5 = format_mood(read.csv("../data/07_exp_away_incongruent_cond5-mood_ratings.csv"))
mood5$Answer.condition = "optimist_incongruent"
mood6 = format_mood(read.csv("../data/07_exp_away_incongruent_cond6-mood_ratings.csv"))
mood6$Answer.condition = "pessimist_incongruent"
mood2$workerid = mood2$workerid + max(mood1$workerid) + 1
mood3$workerid = mood3$workerid + max(mood2$workerid) + 1
mood4$workerid = mood4$workerid + max(mood3$workerid) + 1
mood5$workerid = mood5$workerid + max(mood4$workerid) + 1
mood6$workerid = mood6$workerid + max(mood5$workerid) + 1
mood_all = rbind(mood1, mood2, mood3, mood4, mood5, mood6)
mood1_all = mood_all %>%
filter(type == "mood1") %>%
mutate(mood1 = mood_rating) %>%
mutate(mood_rating = NULL) %>%
mutate(type = NULL)
mood2_all = mood_all %>%
filter(type == "mood2") %>%
mutate(mood2 = mood_rating) %>%
mutate(mood_rating = NULL) %>%
mutate(type = NULL)
mood_all = merge(mood1_all, mood2_all)
mood_by_participant = mood_all
mood_by_participant$diff = mood_all$mood2 - mood_all$mood1
moodp1 = ggplot(data = mood_by_participant) +
geom_bar(mapping = aes(x = workerid, y = diff, fill = Answer.condition), stat = "identity")
moodp1

Exclude random responses
exclude_random = function(d) {
d_overall_means = d %>%
group_by(modal, workerid) %>%
summarise(rating_m_overall = mean(rating))
d_indiv_means = d %>%
group_by(modal,percent_window, workerid) %>%
summarise(rating_m = mean(rating))
d_indiv_merged = merge(d_indiv_means, d_overall_means, by=c("workerid", "modal"))
cors = d_indiv_merged %>%
group_by(workerid) %>%
summarise(corr = cor(rating_m, rating_m_overall))
exclude = cors %>%
filter(corr > 0.75) %>%
.$workerid
print(paste("Excluded", length(exclude), "participants based on random responses."))
d = d %>% filter(!(workerid %in% exclude))
}
d1 = exclude_random(d1)
## [1] "Excluded 18 participants based on random responses."
d2 = exclude_random(d2)
## [1] "Excluded 11 participants based on random responses."
d3 = exclude_random(d3)
## [1] "Excluded 9 participants based on random responses."
d4 = exclude_random(d4)
## [1] "Excluded 14 participants based on random responses."
d5 = exclude_random(d5)
## [1] "Excluded 15 participants based on random responses."
d6 = exclude_random(d6)
## [1] "Excluded 12 participants based on random responses."